Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Occurs
    -0.06
    -h
    -0.06
     danske
    -0.06
    rant
    -0.06
    cool
    -0.06
     ат
    -0.06
    šlo
    -0.06
    .Sound
    -0.06
    -game
    -0.06
    _tpl
    -0.06
    POSITIVE LOGITS
    (#
    0.07
    lib
    0.07
     spoof
    0.07
     tenants
    0.07
     双
    0.06
     redirected
    0.06
    Yaw
    0.06
    STATE
    0.06
    万元
    0.06
    Merc
    0.06
    Act Density 0.000%

    No Known Activations